Site Security and Disruption Incident Agent
The Site Security and Disruption Incident Agent logs and analyses site stoppages, community and business forum disruptions, theft and security incidents. It links each incident to affected programme activities and costs, and prepares evidence packs for extension of time and cost claims, insurance claims and police reports, so disruption is documented properly rather than simply absorbed.
Ideal forProject managers
The difference
From 1-2 days per evidence pack to 2-3 hours
Your team documents incidents fully while facts are fresh, instead of reconstructing them months later for a claim.
Done by hand
1-2 days per evidence pack
With the Vanine agent
2-3 hours
Time returned to your team
80%
Indicative figures. We measure your own baseline in the first fortnight so the numbers you see are yours.
Disruption with a paper trail
Site stoppages and so-called construction mafia disruptions are a real South African project risk. Well-documented incidents give you a stronger basis for time and cost relief under your contract.
Faster insurance and police reporting
Evidence packs with timelines, photos, witness notes and losses are ready when you report to insurers or open a case, saving time when it matters most.
See the true cost of disruption
Linking incidents to programme delays and cost shows management and clients the real impact, supporting decisions on security, community liaison and pricing future work.
Capabilities
Turn site disruptions into documented evidence for claims, insurers and SAPS.
Built for construction managers, contracts managers, security managers and risk teams at South African contractors and developers facing site stoppages, theft and community or business forum disruptions.
Incident logging
Captures each incident from site reports, voice notes, photos and security logs with date, time, location, people involved and immediate actions.
Disruption classification
Classifies incidents as work stoppages, community or business forum disruption, theft, vandalism or security breaches for consistent reporting.
Programme impact
Links incidents to affected activities and the critical path in Primavera P6 or MS Project to show delay impact.
Cost impact
Quantifies standing time for labour and plant, stolen or damaged materials and additional security costs from site and cost records.
Evidence packs
Assembles timelines, photos, diary extracts and correspondence into packs for claims under JBCC, NEC or GCC, insurers and police reports.
Trend analysis
Reports incident patterns by site, type and period, helping management plan security and stakeholder engagement.
How it works
From your systems to a result you sign off
The contracts manager decides which notices and claims are submitted, and an authorised person lays any charge with SAPS or lodges the insurance claim.
Connect the places your incident records already live.
Site diaries, incident reports, security logs, photos and the programme, from Procore, SharePoint or mobile uploads. Already use something else? We connect that too.
- OpenAI Frontier
- Your own AI platform or models
- Microsoft 365 (Teams, SharePoint, Outlook, Excel)
- Copilot Studio
- Primavera P6 and MS Project
- Procore and site diaries
- Security guarding and access control reports
- SharePoint incident libraries
Runs when an incident is reported, or on request in Teams or OpenAI Frontier.
An incident register in Excel, evidence packs in PDF and impact summaries filed in SharePoint.
Step by step
- 01
An incident is reported by the site team or security provider.
- 02
The agent logs and classifies it and gathers photos, diary entries and statements.
- 03
It links the incident to programme and cost impact.
- 04
It assembles the evidence pack for claims, insurers or police.
- 05
The contracts manager reviews the pack and decides on notices and claims.
Deployment
Runs inside the tools your team already uses
The same agent and the same cited output, delivered three ways: through the AI assistant you have rolled out, on a model you host yourself, or inside your own software.
In the frontier assistant you already pay for
We publish the agent as an MCP server. Add it as a connector and your team calls it from the chat they use every day, with no new tool to learn.
"Log the incident from reports and photos"
- incident
- Business forum stoppage
- duration
- 4 days
On a model you host yourself
Run the agent on open-weight models in your data centre or private cloud. Your incident records never leave your network, which keeps POPIA and data residency straightforward.
- Llama
- Mistral
- Ollama
- or any OpenAI-compatible endpoint
Inside your own software
Trigger a run from your own workflows, and push the finished output into your ERP, GRC or reporting systems. We build the integration with your team.
- REST API
- Webhooks
- Batch jobs
- Embeddable review panel
Governed the same way, every route
Whichever way your team reaches the agent, identity, permissions and audit stay with your existing controls.
- Single sign-on through Entra ID, Okta or Google Workspace
- Reads only the documents each user is already allowed to open
- Every tool call written to an audit log you can export
How we deliver it
One agent, three ways to hold it
Start where your team already works, then take it as far into your systems as the value justifies.
DATA SECURITY & PRIVACY
Your incident records stay yours.
The agent runs inside your tenancy, reads only what each task needs, and never trains on your incident records. Every step is logged so your auditors can see exactly what it touched.
Built for regulated work.
+YOUR INCIDENT RECORDS NEVER LEAVE YOUR ENVIRONMENT
More agents
More agents we build for South African enterprises
Each one is built on the same foundation: your documents, your rules, and your people signing off.
Precision AI for Institutional Workflows
